Large language models (LLMs) have recently demonstrated the potential in acting as autonomous agents for sequential decision-making tasks. However, most existing methods either take actions greedily without planning or rely on static plans that are not adaptable to environmental feedback. Consequently, the sequential decision-making performance of LLM agents degenerates with problem complexity and plan horizons increase. We propose a closed-loop approach, AdaPlanner, which allows the LLM agent to refine its self-generated plan adaptively in response to environmental feedback. In AdaPlanner, the LLM agent adaptively refines its plan from feedback with both in-plan and out-of-plan refinement strategies. To mitigate hallucination, we develop a code-style LLM prompt structure that facilitates plan generation across a variety of tasks, environments, and agent capabilities. Furthermore, we propose a skill discovery mechanism that leverages successful plans as few-shot exemplars, enabling the agent to plan and refine with fewer task demonstrations. Our experiments in the ALFWorld and MiniWoB++ environments demonstrate that AdaPlanner outperforms state-of-the-art baselines by 3.73% and 4.11% while utilizing 2x and 600x fewer samples, respectively.
SKL of Processors, Institute of Computing Technology, CAS, Beijing, China(处理器SKL,计算技术研究所,中国科学院,北京);University of Chinese Academy of Sciences, Beijing, China(中国科学院大学,北京);Cambricon Technologies, Beijing, China(寒武纪科技,北京);SKL of Computer Science, Institute of Software, CAS, Beijing, China(计算机科学SKL,软件研究所,中国科学院,北京);Shanghai Innovation Center for Processor Technologies, SHIC, Shanghai, China(上海处理器技术创新中心,SHIC,上海,中国);University of Science and Technology of China(中国科学技术大学);Autodesk Research(Autodesk研究)
Mutual Enhancement of Large Language and Reinforcement Learning Models through Bi-Directional Feedback Mechanisms: A Planning Case Study
Technical University of Munich(慕尼黑工业大学);Peking University(北京大学);BIGAI(北京智源人工智能研究院);King's College London(伦敦国王学院);Tongji University(同济大学);University College London(伦敦大学学院)
CityPlanner: A Sandbox Agent for Executable Urban Planning
School of Computer Science and Engineering, Beihang University(北京航空航天大学计算机科学与工程学院);MIIT Key Laboratory of Data and Decision Intelligence, Beihang University(北京航空航天大学工业和信息化部数据与决策智能重点实验室)
Agent-RewardBench: Towards a Unified Benchmark for Reward Modeling across Perception, Planning, and Safety in Real-World Multimodal Agents
The Key Laboratory of Cognition and Decision Intelligence for Complex Systems, Institute of Automation, Chinese Academy of Sciences(认知与决策智能复杂系统重点实验室,自动化研究所,中国科学院);School of Artificial Intelligence, University of Chinese Academy of Sciences(人工智能学院,中国科学院大学)
ProtoCycle: Reflective Tool-Augmented Planning for Text-Guided Protein Design
Shanghai Jiao Tong University, School of Mathematical Sciences(上海交通大学数学科学学院);DP Technology(DP技术);University of Science and Technology of China(中国科学技术大学);AI for Science Institute(AI for Science研究院)
Agent Planning Benchmark: A Diagnostic Framework for Planning Capabilities in LLM Agents
Tongji University(同济大学);Shanghai AI Laboratory(上海人工智能实验室);Harbin Institute of Technology(哈尔滨工业大学);Fudan University(复旦大学);Skywork AI;University of California, Santa Cruz(加州大学圣克鲁兹分校);Shanghai Jiao Tong University(上海交通大学);The Chinese University of Hong Kong(香港中文大学)